© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27118
    Prev
    Next
    INDEX
    Explanations

    terms related to project management and administration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    280
    +0.13
    0.7%
    402
    +0.13
    0.7%
    184
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.13
    0.01
    365
    +0.13
    0.01
    184
    +0.12
    0.01
    Negative Logits
    webs
    -1.62
     footsteps
    -1.52
     minds
    -1.46
     veins
    -1.45
    ĨĴ
    -1.45
    bies
    -1.42
    odend
    -1.37
     versus
    -1.36
     students
    -1.36
     morning
    -1.35
    POSITIVE LOGITS
    ionale
    1.79
     {
    1.57
    ions
    1.53
    ional
    1.50
    {
    1.49
    iant
    1.47
     cond
    1.47
    oner
    1.41
    tin
    1.40
    imental
    1.40
    Activations Density 0.057%

    No Known Activations